CNN 기반 딥러닝을 이용한 임베디드 리눅스 양각 문자 인식 시스템 구현

An Implementation of Embedded Linux System for Embossed Digit Recognition using CNN based Deep Learning

  • 유연승 (남서울대학교 컴퓨터소프트웨어학과) ;
  • 김정길 (남서울대학교 컴퓨터소프트웨어학과) ;
  • 홍충표 (LG전자 CTO부문)
  • 투고 : 2020.06.25
  • 심사 : 2020.06.26
  • 발행 : 2020.06.30

초록

Over the past several years, deep learning has been widely used for feature extraction in image and video for various applications such as object classification and facial recognition. This paper introduces an implantation of embedded Linux system for embossed digits recognition using CNN based deep learning methods. For this purpose, we implemented a coin recognition system based on deep learning with the Keras open source library on Raspberry PI. The performance evaluation has been made with the success rate of coin classification using the images captured with ultra-wide angle camera on Raspberry PI. The simulation result shows 98% of the success rate on average.

키워드

참고문헌

  1. Min, Y., Choi, H., " Introduction to Deep Learning and hot issues", Korea Information Processing Society Review, vol. 22, pp.7-21, 2015.
  2. Lee, S., Jeong, J., "2020 AI Top 7 Trends"- Beyond Perception, ETRI Insight, Insight Report 2019-57
  3. Lee, Y., Lee,Y., "Implementation of Moving Object Recognition based on Deep Learning", J. of the Semiconductor &Display Technology, Vol.17, No.1, pp.67-70, 2009.
  4. Lee, Y., Kim, Y., "Comparison of CNN and YOLO for Object Detection", J. of the Semiconductor & Display Technology Vol.19, No.1, pp.85-92, 2020.
  5. Kim, J., Cho, W., Na, M., Chun, M., "Development of Automatic Classification System of Vegetables by Image Processing and Deep Learning", J. of the Korean Data Analysis Society VOL.21 NO.1, pp. 63-73, 2019. https://doi.org/10.37727/jkdas.2019.21.1.63
  6. Kim, M., Shin, S., Suh, Y., "Application of Deep Learning Algorithm for Detecting Construction Workers Wearing Safety Helmet Using Computer Vision", J. of the Korean Society of Safety Vol. 34, No. 6, pp. 29-37, 2019. https://doi.org/10.14346/JKOSOS.2019.34.6.29
  7. Kim, D., "A Study on Target Detection and Tracking via Drones Using Deep Learning and Computer Vision", The Graduate School of Korea Aerospace University 2020
  8. Yi, H., Bui, K., Seon, C., "A Deep Learning LSTM Framework for Urban Traffic Flow and Fine Dust Prediction", J. of KIISE, Vol.47, No.3, pp. 292-297, 2020. https://doi.org/10.5626/jok.2020.47.3.292
  9. Chu,Y., Choi, Y., "A Deep Learning based IOT Device Recognition System", J. of the Semiconductor & Display Technology, Vol.18, No.2, pp.1-5, 2019.
  10. Yun, H., Park, K., Kim, D., "A Study on the Improvement of Intaglio Characters Recognition of Rubber Tires", J. of the Korea Convergence Society, Vol.9, No.10 pp. 7-12, 2018. https://doi.org/10.15207/JKCS.2018.9.10.007
  11. Baek, S., Kim, K., Jang, J., "Implementation of Car tire information recognition system using laser range sensor", J. of Korean Institute of Communications and Information Science, Vol.2016, No.1, pp. 123-124 2016.
  12. Lee, T., Cha, J., Ryu, B., Kim. J., "Deep Learning based Test Detection in P & ID Images", J. of Mechanical Science and Technology, Vol.2019,No.5, pp. 114-115, 2019
  13. K. Team, "Keras: the Python deep learning API", Keras.io, 2020. [Online]. Available: https://keras.io/.
  14. "TensorFlow", TensorFlow, 2020. [Online]. Available: https://www.tensorflow.org/ [Accessed: 05- Jun- 2020]
  15. H. Partnership, "OpenCV", Opencv.org, 2020. [Online]. Available: https://opencv.org/.
  16. Ji, S., Baek, U., Shin, M., Char, B., Moon, H., Kim, M., "Design of Web Application Traffic Classification Model Based on Convolution Neural Network", J. of Korean Institute of Communications and Information Science, Vol.44, No.06, pp. 1113-1120 2019. https://doi.org/10.7840/kics.2019.44.6.1113
  17. Ahn, H., Lee, Y., "A Research of CNN-based Object Detection for Multiple Object Tracking in Image", J. of the Semiconductor & Display Technology, Vol.18, No.3, pp.110-114, 2019.
  18. N. Ketkar, Deep Learning with Python. [Place of publication not identified]: Apress, 2017.
  19. Lim, H., Kim, J., Kwon, D., Han, Y., "Comparison Analysis of TensorFlow's Optimizer Based on MNIST's CNN Model", Journal of Advanced Technology Research, vol. 2, no. 1, pp. 6-14, 2020. .
  20. Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R., "Dropout: a simple way to prevent neural networks from overfitting.", J. of Machine Learning Research, Vol.15, No.1, pp.1929-1958, 2014.